Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    ch words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     minimally
    0.80
     true
    0.77
     ultimate
    0.72
     end
    0.68
     Prof
    0.67
     let
    0.67
     integration
    0.66
     QE
    0.66
     intuitive
    0.66
     implicitly
    0.66
    POSITIVE LOGITS
    ampions
    0.94
    ocolate
    0.93
    izophren
    0.91
    イルド
    0.91
    ract
    0.89
    ristmas
    0.88
    attering
    0.88
    icago
    0.88
    allenge
    0.88
    usetts
    0.87
    Act Density 0.075%

    No Known Activations